[AMDGPU] Add RDNA4 targets and WMMA #20048
Merged
+558
−110
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
krzysz00
requested review from
kuhar,
antiagainst,
MaheshRavishankar,
qedawkins,
Groverkss and
hanhanW
as code owners
krzysz00
changed the title
kuhar
reviewed
Feb 24, 2025
compiler/src/iree/compiler/Codegen/Common/GPU/test/gpu_nested_layout_contract_amdgpu.mlir
Outdated
Show resolved
Hide resolved
compiler/src/iree/compiler/Codegen/Dialect/GPU/TargetUtils/KnownTargets.cpp
Outdated
Show resolved
Hide resolved
bjacob
approved these changes
Feb 24, 2025
Add gfx1200 and gfx1201 as supported targets, copying RDNA3 for now. This target definition isn't correct - the WMMA definitions have changed - but it at least works as a first commit.
… and obviously use it
krzysz00
force-pushed
the
users/krzysz00/gfx12
branch
from
15e8e42 to
9edecf1
Compare
|
A poower of two. |
|
@bjacob I'm not seeing the typo in my PR? |
|
Sorry, I was looking at the PR number. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds definitions for the new WMMAs in RDNA 4, adds a target definition, and updates tetsts.
The WMMA instructions have changed semantics (half as many inputs per lane, no more weird broadcast thing and a different output) from RDNA3 so we now have WMMAR3 and WMMAR4 variants (the R4 are 0x19** in the enum). Some tests are duplicated, some aren't yet. This is an initial PR to enable RDNA4 bringup.